<?xml version="1.0" encoding="utf-8" standalone="yes" ?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Weisi Lin | ViLab</title>
    <link>https://vilab.team/author/weisi-lin/</link>
      <atom:link href="https://vilab.team/author/weisi-lin/index.xml" rel="self" type="application/rss+xml" />
    <description>Weisi Lin</description>
    <generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Mon, 27 Oct 2025 00:00:00 +0000</lastBuildDate>
    <image>
      <url>https://vilab.team/media/icon_hu2896232876136423579.png</url>
      <title>Weisi Lin</title>
      <link>https://vilab.team/author/weisi-lin/</link>
    </image>
    
    <item>
      <title>DT-UFC: Universal large model feature coding via peaky-to-balanced distribution transformation</title>
      <link>https://vilab.team/publication/dt-ufc-universal-large-model-feature-coding-via-peaky-to-bal/</link>
      <pubDate>Mon, 27 Oct 2025 00:00:00 +0000</pubDate>
      <guid>https://vilab.team/publication/dt-ufc-universal-large-model-feature-coding-via-peaky-to-bal/</guid>
      <description>&lt;p&gt;本文首次系统研究大模型通用特征编码问题，旨在降低分布式部署中的传输与存储开销。针对不同模型提取特征分布差异显著（如DINOv2特征高度集中、SD3特征分散均匀）导致压缩效率低、跨模型泛化难的问题，提出一种从峰值分布到平衡分布的变换方法，实现通用且高效的特征压缩与传输。&lt;/p&gt;
</description>
    </item>
    
  </channel>
</rss>
